Gemini 2.5 Pro
2M-token context + native multimodality — unbeatable for huge docs.
Intelligence index
78/ 100
vs all models86th pctile
Composite of MMLU, GPQA, MATH & HumanEval
Speed
110tok/s
vs all models59th pctile
Median across providers, steady state
Blended price
$2.19/ 1M tokens
vs all models50th pctile
3:1 input:output blend
At a glance
- Context window
- 2M tokens
- Max output
- 66k tokens
- Input price
- $1.25 / 1M tokens
- Output price
- $5.00 / 1M tokens
- Time to first token
- 0.7s
- Input modalities
- text, image, audio, video
- Output modalities
- text
- License
- Proprietary
- Provider
Benchmark scores
Public scores from each provider; bars compare this model against the leader in each benchmark.
MMLU
General knowledge across 57 subjects
89.5
leader: 91.8
MMLU Pro
Harder MMLU successor with more reasoning
78.5
leader: 80.0
GPQA
Graduate-level science Q&A
66.0
leader: 78.0
MATH
Competition mathematics
91.0
leader: 94.8
HumanEval
Python code generation pass@1
91.5
leader: 95.8
Strengths
- 2M context
- Native video understanding
- Strong on math
Weaknesses
- Output ceiling lower than competitors
Best for
- Whole-codebase analysis
- Long-doc workflows
- Video QA
Models you should also evaluate
OpenAI
GPT-5.5
OpenAI’s 2026 flagship — strongest at reasoning, coding and tool use.
82 intel95 tok/s$7.50 /1M
Anthropic
Claude 4 Opus
Anthropic’s 2026 flagship — best-in-class on code and long-horizon agents.
81 intel50 tok/s$16.00 /1M
xAI
Grok 3
Real-time data via X — competitive on reasoning, 1M context.
74 intel75 tok/s$6.00 /1M
Gemini 2.5 Pro vs… popular head-to-heads
One-click matchups against the models people compare Gemini 2.5 Pro with most.
Gemini 2.5 Pro — frequently asked questions
Gemini 2.5 Pro is a large language model from Google, released on 15 September 2025. 2M-token context + native multimodality — unbeatable for huge docs.
Need help choosing between models?
Compare every option in one sortable table — intelligence, speed and price on a single page.